EvalGate

com.evalgatePublished by evalgate.comOfficial publisherv1.0.0Updated Nov 5, 2026

Run AI evaluations, record agent traces and gate releases on evidence, with scoped org access.

VerifiedStreamable HTTPWeb executableDeveloper ToolsAI & ML

Overview

AI-generated overview

EvalGate is a remote MCP server for inspecting AI evaluation projects, runs, baselines and connector health in an authenticated organization.

What you can do
  • Inspect the organization's evaluations, project keys and connector definitions, including installed setup paths and account roots.
  • List evaluations and evaluation runs with stable cursors and regression signals.
  • Explain a run from its status, failed-case metadata and evidence lineage, and show the published baseline anchor.
  • Review connector readiness reports and workspace connection metadata, references and visible resource revisions.
  • Search the published OpenAPI operation catalog for help and get a non-mutating next-step plan for connecting a repository, evaluation or trace source.
When to use it
Useful when an assistant needs to read and explain AI evaluation results, regressions and baselines, or check whether connectors and trace sources are ready, without changing anything. Suited to teams already using EvalGate for evaluation and release gating.
Requirements
A remote streamable HTTP endpoint at the EvalGate site; no package, environment variables or headers are declared. Access is scope-filtered to an authenticated organization, so an EvalGate account with the appropriate scopes is needed.
Before you install
The server states that tools are scope-filtered and that write tools such as evaluations_create, test_cases_add, runs_start and traces_create require a matching write scope and pass through quota, lock and audit checks; approval and baseline acceptance are separate actions. The listed tools are read-oriented, but connection metadata and lineage are exposed to the assistant.

Installation

In SourceWeft

  1. Open EvalGate in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.evalgate%2Fevalgate/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "evalgate": {
      "type": "http",
      "url": "https://www.evalgate.com/api/mcp"
    }
  }
}

Tools

12

project_inspect

Inspect the evaluations and project keys available in the authenticated organization.

ParametersprojectKey

project_plan

Return a non-mutating next-step plan for connecting a repository, evaluation, or trace source.

Parameterstarget

evaluations_list

List evaluations with a stable cursor for the organization.

Parameterslimitcursorstatus

runs_list

List evaluation runs with stable cursors and regression signals.

ParameterslimitcursorstatusevaluationIdrequired

run_explain

Explain a run using its status, failed-case metadata, and evidence-lineage summary.

ParametersrunIdrequired

baseline_lineage

Show the published baseline anchor and its evidence lineage.

ParametersevaluationIdrequired

connector_health

Show the latest connector-readiness reports for the organization.

ParametersconnectorKey

connections_list

List current workspace connection metadata, with source restrictions, freshness and bounded continuation. Does not reveal secrets or grant source access.

Parametersqlimitcursorsource

connections_catalog

Inspect all connector definitions and exact installed setup paths. Unavailable blueprints and live verification are separate facts.

Takes no parameters.

connections_roots

Page independent configured account roots using current administrator authority. Does not list secrets or imply verified connector availability.

Parametersqlimitcursor

connections_graph

Read canonical connection references and currently visible exact resource revisions. No source access grant or execution.

Parametersidrequired

Version history

1
  1. v1.0.0LatestNov 5, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Evalgate integrations

EvalGate Docs

com.evalgateOfficial publisher

Read-only remote MCP server that lets an assistant list, search and read EvalGate's published documentation pages.

Streamable HTTPWeb executable
Knowledge & Memory3 toolsNov 5, 2026

EvalGate

Published by GitHub account evalgate

Remote EvalGate MCP server that lets an assistant inspect AI evaluations, runs, baselines and connector health for an organization.

Streamable HTTPWeb executableAuth
Data & Analytics12 toolsOct 26, 2026

Evalgate

Published by GitHub account ipezygj

A local MCP server that runs statistical checks on AI evaluation results before an assistant treats a reported score as trustworthy.

STDIODesktop only
AI & MLNot validated yetOct 24, 2026